Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.3405. Min Act: -0.1700
Data Index: 2750481 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.3405. Min Act: -0.1700
Data Index: 951698 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.2780. Min Act: -0.1700
Data Index: 491695 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.2780. Min Act: -0.1700
Data Index: 3590876 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.1842. Min Act: -0.1700
Data Index: 251917 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.1842. Min Act: -0.1700
Data Index: 1128456 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.1842. Min Act: -0.1700
Data Index: 5727338 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.1530. Min Act: -0.1700
Data Index: 1752863 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.1217. Min Act: -0.1700
Data Index: 4659402 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.0905. Min Act: -0.1700
Data Index: 4750770 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.0905. Min Act: -0.1700
Data Index: 944334 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.0592. Min Act: -0.1700
Data Index: 6090851 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.0592. Min Act: -0.1700
Data Index: 7510753 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.0592. Min Act: -0.1700
Data Index: 6681315 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3405. Min Range: -6.3405
Max Act: 5.9967. Min Act: -0.1700
Data Index: 3613454 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.0592. Min Act: -0.1700
Data Index: 3792619 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3405. Min Range: -6.3405
Max Act: 6.0280. Min Act: -0.1700
Data Index: 6728761 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3405. Min Range: -6.3405
Max Act: 5.9967. Min Act: -0.1700
Data Index: 3590878 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3405. Min Range: -6.3405
Max Act: 5.9967. Min Act: -0.1700
Data Index: 640283 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3405. Min Range: -6.3405
Max Act: 5.9967. Min Act: -0.1700
Data Index: 6812996 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19